© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85796
    Prev
    Next
    INDEX
    Explanations

    electronegativity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    S
    0.44
    N
    0.43
     رس
    0.42
    subtype
    0.40
    اره
    0.40
    ಞ
    0.40
     skilled
    0.40
    。”
    0.39
    持
    0.39
    織
    0.39
    POSITIVE LOGITS
     cani
    0.50
     Cann
    0.48
     remporté
    0.48
     AcOEt
    0.47
     alkal
    0.46
     cruiser
    0.46
    faat
    0.45
     alınd
    0.45
     Giul
    0.45
     favoriser
    0.45
    Activations Density 0.001%

    No Known Activations